Additional Wonderless Stats

Dependencies

if (!require(tidyverse))
  install.packages("tidyverse")

Loading required package: tidyverse
Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.3.1 ──
✓ ggplot2 3.3.3     ✓ purrr   0.3.4
✓ tibble  3.1.2     ✓ dplyr   1.0.6
✓ tidyr   1.1.3     ✓ stringr 1.4.0
✓ readr   1.4.0     ✓ forcats 0.5.1
── Conflicts ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

library(tidyverse)
if (!require(viridis))
  install.packages("viridis")

Loading required package: viridis
Loading required package: viridisLite

library(viridis)
if (!require(gh))
  install.packages("gh")

Loading required package: gh

library(gh)
if (!require(jsonlite))
  install.packages("jsonlite")

Loading required package: jsonlite

Attaching package: ‘jsonlite’

The following object is masked from ‘package:purrr’:

    flatten

library(jsonlite)
if (!require(DT))
  install.packages('DT')

Loading required package: DT
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

library(DT)

Configure GH API

Set ghToken GitHub personal access token with public access in order to authenticate with their API.

ghToken <- 'ghp_XXX'

ghAuth <- function(...) {
  gh(..., .token=ghToken)
}
ghAllPages <- function(...) {
  result <- list()
  i <- 0
  repeat {
    i <- i + 1
    newElements <- NA
    tryCatch({
      newElements <- ghAuth(..., per_page=100, page=i)
    }, error=function(e) {
      if (is(e, 'http_error_404') & i == 1) return(NA)
      else return(e)
    })
    if (anyNA(newElements)) return(NA)
    result <- append(result, newElements)
    if (length(newElements) < 100) return(result)
  }
}

Load Repos

repo_urls <- read.csv2('./dataset.csv') %>% transmute(repoUrl = Project.URLs)
repo_urls

Releases and Tags

To fetch tags and releases uncomment download and JSON export code.

#repoTagsReleases <- repo_urls %>%
#  mutate(owner=map_chr(repoUrl, ~ str_split(.x, '/')[[1]][4]),
#         repo=map_chr(repoUrl, ~ str_split(.x, '/')[[1]][5]),
#         tags=pmap(list('GET /repos/{owner}/{repo}/tags', owner=owner, repo=repo), ghAllPages),
#         tagsCount=map_int(tags, ~ if (anyNA(.x)) NA else length(.x)),
#         releases=pmap(list('GET /repos/{owner}/{repo}/releases', owner=owner, repo=repo), ghAllPages),
#         releasesCount=map_int(releases, ~ if (anyNA(.x)) NA else length(.x)))
#
#exportJSON <- toJSON(repoTagsReleases)
#write(exportJSON, 'repositories-tags-releases.json')

repoTagsReleases <- fromJSON('repositories-tags-releases.json')
repoTagsReleases %>% datatable()

Warning in instance$preRenderHook(instance) :
  It seems your data is too big for client-side DataTables. You may consider server-side processing: https://rstudio.github.io/DT/server.html
Warning in instance$preRenderHook(instance) :
  It seems your data is too big for client-side DataTables. You may consider server-side processing: https://rstudio.github.io/DT/server.html

GitHub Actions Workflows

ghActionWorkflows <- read.csv2('./gh-actions-workflows.txt', header=FALSE, col.names=c('ghActionWorkflow')) %>%
  mutate(project=map_chr(ghActionWorkflow, ~ str_split(.x, '/')[[1]][3]))
ghActionWorkflowRepos <- ghActionWorkflows %>% group_by(project) %>% summarise(ghActionWorkflows=list(ghActionWorkflow), ghActionsWorkflowsCount=n()) %>% ungroup()
ghActionWorkflowRepos %>% datatable()

Amazon States Language

aslWorkflows <- read.csv2('./asl.txt', header=FALSE, col.names=c('aslWorkflow')) %>%
  mutate(project=map_chr(aslWorkflow, ~ str_split(.x, '/')[[1]][3]))
aslWorkflowRepos <- aslWorkflows %>% group_by(project) %>% summarise(aslWorkflows=list(aslWorkflow), aslWorkflowsCount=n()) %>% ungroup()
aslWorkflowRepos %>% datatable()

Airflow

airflowWorkflows <- read.csv2('./airflow.txt', header=FALSE, col.names=c('airflowWorkflow')) %>%
  mutate(project=map_chr(airflowWorkflow, ~ str_split(.x, '/')[[1]][3]))
airflowWorkflowRepos <- airflowWorkflows %>% group_by(project) %>% summarise(airflowWorkflows=list(airflowWorkflow), airflowWorkflowsCount=n()) %>% ungroup()
airflowWorkflowRepos %>% datatable()

Summary

reposSummary <- repoTagsReleases %>% mutate(project=paste(owner, repo, sep='_')) %>%
  full_join(ghActionWorkflowRepos, by='project') %>%
  full_join(aslWorkflowRepos, by='project') %>%
  full_join(airflowWorkflowRepos, by='project')
reposSummary %>% datatable()

Warning in instance$preRenderHook(instance) :
  It seems your data is too big for client-side DataTables. You may consider server-side processing: https://rstudio.github.io/DT/server.html
Warning in instance$preRenderHook(instance) :
  It seems your data is too big for client-side DataTables. You may consider server-side processing: https://rstudio.github.io/DT/server.html